A
Anoop Kolar Rajagopal
Researcher at Indian Institute of Science
Publications - 12
Citations - 273
Anoop Kolar Rajagopal is an academic researcher from Indian Institute of Science. The author has contributed to research in topics: Transfer of learning & Pose. The author has an hindex of 6, co-authored 12 publications receiving 137 citations.
Papers
More filters
Posted ContentDOI
Progressive Fashion Attribute Extraction.
TL;DR: This work proposes a progressive training approach for multi-class classification of fashion attributes, where weights learnt from an attribute are fine tuned for another attribute of the same fashion article (say, dresses).
Journal ArticleDOI
Exploring Transfer Learning Approaches for Head Pose Classification from Multi-view Surveillance Images
Anoop Kolar Rajagopal,Ramanathan Subramanian,Elisa Ricci,Radu L. Vieriu,Oswald Lanz,Ramakrishnan Kalpathi,Nicu Sebe +6 more
TL;DR: This paper examines the use of transfer learning for efficient multi-view head pose classification with minimal target training data under three challenging situations: (i) where the range of head poses in the source and target images is different, (ii) where source images captured a stationary person while target images capture a moving person whose facial appearance varies under motion due to changing perspective, scale.
Proceedings ArticleDOI
Deep automatic license plate recognition system
Vishal Jain,Zitha Sasindran,Anoop Kolar Rajagopal,Soma Biswas,Harish S Bharadwaj,K. R. Ramakrishnan +5 more
TL;DR: This work aims to address ALPR using Deep CNN methods for real-time traffic videos using a CNN classifier trained for individual characters along with a spatial transformer network (STN) for character recognition.
Book ChapterDOI
An adaptation framework for head-pose classification in dynamic multi-view scenarios
Anoop Kolar Rajagopal,Ramanathan Subramanian,Radu L. Vieriu,Elisa Ricci,Oswald Lanz,K. R. Ramakrishnan,Nicu Sebe +6 more
TL;DR: A transfer learning approach that incorporates reliability of the different face regions for pose estimation under positional variation, by transforming the target appearance to a canonical appearance corresponding to a reference scene location.
Journal ArticleDOI
Online Estimation of Evolving Human Visual Interest
TL;DR: An interactive human-in-the-loop framework to model eye movements and predict visual saliency into yet-unseen frames and a novel statistical- and algorithm-based method gaze buffering is proposed for eye-gaze analysis and its fusion with content-based features.